Home Explore Help
Sign In
RONCC
/
Machine-Learning-Training
Watch 1
Star 0
Fork 0
Files Issues 0 Pull Requests 0 Wiki
Browse Source

Add kaggle data

Wael BADER 3 years ago
parent
b538dd16a1
commit
b6cecbacd4
9 changed files with 17650 additions and 210 deletions
Split View Show Diff Stats
  1. 827 59
      01-PCA.ipynb
  2. 739 44
      02-FeatureProcessing.ipynb
  3. 1996 107
      03-ProjectIntro.ipynb
  4. 2001 0
      data/kaggle_data/dummy-solution.csv
  5. 43 0
      data/kaggle_data/features-description.txt
  6. 43 0
      data/kaggle_data/features.txt
  7. 2000 0
      data/kaggle_data/test-val.csv
  8. 5001 0
      data/kaggle_data/train-targets.csv
  9. 5000 0
      data/kaggle_data/train.csv

File diff suppressed because it is too large
+ 827 - 59
01-PCA.ipynb


File diff suppressed because it is too large
+ 739 - 44
02-FeatureProcessing.ipynb


File diff suppressed because it is too large
+ 1996 - 107
03-ProjectIntro.ipynb


File diff suppressed because it is too large
+ 2001 - 0
data/kaggle_data/dummy-solution.csv


+ 43 - 0
data/kaggle_data/features-description.txt
View File 

@@ -0,0 +1,43 @@
 
+'nb_words_title'  Number of words in the article's titles
 
+'nb_words_content'  Number of words in the article
 
+'pp_uniq_words'  Proportion of unique words in the article
 
+'pp_stop_words' Proportion of stop words (i.e. words predefined to be too common to be of use for interpretation or queries, such as 'the', 'a', 'and', etc.)
 
+'pp_uniq_non-stop_words'  Proportion of non-stop words among unique words
 
+'nb_links'  Number of hyperlinks in the article
 
+'nb_outside_links'  Number of hyperlinks pointing to another website
 
+'nb_images'  Number of images in the article
 
+'nb_videos'  Number of videos in the article
 
+'ave_word_length'  Average word length
 
+'nb_keywords'  Number of keywords in the metadata
 
+'category'  Category of the article: 0-Lifestyle, 1-Entertainment, 2-Business, 3-Web, 4-Tech, 5-World
 
+'nb_mina_mink'  Minimum number of share counts among all articles with at least one keyword in common with the article
 
+'nb_mina_maxk'  Minimum number of maximum share counts per keyword
 
+'nb_mina_avek'  Minimum number of average share counts per keyword
 
+'nb_maxa_mink'  Maximum number of minimum share counts per keyword
 
+'nb_maxa_maxk'  Maximum number of share counts among all articles with at least one keyword in common with the article
 
+'nb_maxa_avek'  Maximum number of average share counts per keyword
 
+'nb_avea_mink'  Average number of minimum share counts per keyword
 
+'nb_avea_maxk'  Average number of maximum share counts per keyword
 
+'nb_avea_avek'  Average number of average share counts per keyword
 
+'nb_min_linked'  Minimum number of shares of articles from the same website linked within the article
 
+'nb_max_linked'  Maximum number of shares of articles from the same website linked within the article
 
+'nb_ave_linked'  Average number of shares of articles from the same website linked within the article
 
+'weekday'  Day of the week: 0-Monday, 1-Tuesday, 2-Wednesday, until 6-Sunday
 
+'dist_topic_0'  Distance to topic 0
 
+'dist_topic_1'  Distance to topic 1
 
+'dist_topic_2'  Distance to topic 2
 
+'dist_topic_3'  Distance to topic 3
 
+'dist_topic_4'  Distance to topic 4
 
+'subj'  Subjectivity
 
+'polar'  Sentiment polarity 
+'pp_pos_words'  Proportion of positive words in the article
 
+'pp_neg_words'  Proportion of negative words in the article
 
+'pp_pos_words_in_nonneutral'  Proportion of positive words among the non-neutral words of the article
 
+'ave_polar_pos'  Average sentiment polarity of the positive words
 
+'min_polar_pos'  Minimum sentiment polarity of the positive words
 
+'max_polar_pos'  Maximum sentiment polarity of the positive words
 
+'ave_polar_neg'  Average sentiment polarity of the negative words
 
+'min_polar_neg'  Mimimum sentiment polarity of the negative words
 
+'max_polar_neg'  Maximum sentiment polarity of the negative words
 
+'subj_title'  Subjectivity of the title
 
+'polar_title'  Polarity of the title

+ 43 - 0
data/kaggle_data/features.txt
View File 

@@ -0,0 +1,43 @@
 
+'nb_words_title'  Number of words in the article's titles
 
+'nb_words_content'  Number of words in the article
 
+'pp_uniq_words'  Proportion of unique words in the article
 
+'pp_stop_words'  Proportion of stop words (i.e. words predefined to be too common to be of use for interpretation or queries, such as 'the', 'a', 'and', etc.)
 
+'pp_uniq_non-stop_words'  Proportion of non-stop words among unique words
 
+'nb_links'  Number of hyperlinks in the article
 
+'nb_outside_links'  Number of hyperlinks pointing to another website
 
+'nb_images'  Number of images in the article
 
+'nb_videos'  Number of videos in the article
 
+'ave_word_length'  Average word length
 
+'nb_keywords'  Number of keywords in the metadata
 
+'category'  Category of the article: 0-Lifestyle, 1-Entertainment, 2-Business, 3-Web, 4-Tech, 5-World
 
+'nb_mina_mink'  Minimum number of share counts among all articles with at least one keyword in common with the article
 
+'nb_mina_maxk'  Minimum number of maximum share counts per keyword
 
+'nb_mina_avek'  Minimum number of average share counts per keyword
 
+'nb_maxa_mink'  Maximum number of minimum share counts per keyword
 
+'nb_maxa_maxk'  Maximum number of share counts among all articles with at least one keyword in common with the article
 
+'nb_maxa_avek'  Maximum number of average share counts per keyword
 
+'nb_avea_mink'  Average number of minimum share counts per keyword
 
+'nb_avea_maxk'  Average number of maximum share counts per keyword
 
+'nb_avea_avek'  Average number of average share counts per keyword
 
+'nb_min_linked'  Minimum number of shares of articles from the same website linked within the article
 
+'nb_max_linked'  Maximum number of shares of articles from the same website linked within the article
 
+'nb_ave_linked'  Average number of shares of articles from the same website linked within the article
 
+'weekday'  Day of the week: 0-Monday, 1-Tuesday, 2-Wednesday, until 6-Sunday
 
+'dist_topic_0'  Distance to topic 0
 
+'dist_topic_1'  Distance to topic 1
 
+'dist_topic_2'  Distance to topic 2
 
+'dist_topic_3'  Distance to topic 3
 
+'dist_topic_4'  Distance to topic 4
 
+'subj'  Subjectivity
 
+'polar'  Sentiment polarity 
+'pp_pos_words'  Proportion of positive words in the article
 
+'pp_neg_words'  Proportion of negative words in the article
 
+'pp_pos_words_in_nonneutral'  Proportion of positive words among the non-neutral words of the article
 
+'ave_polar_pos'  Average sentiment polarity of the positive words
 
+'min_polar_pos'  Minimum sentiment polarity of the positive words
 
+'max_polar_pos'  Maximum sentiment polarity of the positive words
 
+'ave_polar_neg'  Average sentiment polarity of the negative words
 
+'min_polar_neg'  Mimimum sentiment polarity of the negative words
 
+'max_polar_neg'  Maximum sentiment polarity of the negative words
 
+'subj_title'  Subjectivity of the title
 
+'polar_title'  Polarity of the title

File diff suppressed because it is too large
+ 2000 - 0
data/kaggle_data/test-val.csv


File diff suppressed because it is too large
+ 5001 - 0
data/kaggle_data/train-targets.csv


File diff suppressed because it is too large
+ 5000 - 0
data/kaggle_data/train.csv